First Push

README.md

@@ -0,0 +1,35 @@
+---
+library_name: ml-agents
+tags:
+- SnowballTarget
+- deep-reinforcement-learning
+- reinforcement-learning
+- ML-Agents-SnowballTarget
+---
+
+  # **ppo** Agent playing **SnowballTarget**
+  This is a trained model of a **ppo** agent playing **SnowballTarget**
+  using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
+
+  ## Usage (with ML-Agents)
+  The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
+
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+  - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
+  browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
+  - A *longer tutorial* to understand how works ML-Agents:
+  https://huggingface.co/learn/deep-rl-course/unit5/introduction
+
+  ### Resume the training
+  ```bash
+  mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
+  ```
+
+  ### Watch your Agent play
+  You can watch your agent **playing directly in your browser**
+
+  1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
+  2. Step 1: Find your model_id: smiley-maker/ppo-SnowballTarget2
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

SnowballTarget.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8cf3d8f49f9b8fda5bde914bb99dec1f2fdbb7d59d3c7f8fd5658f57a151beb
+size 271829

SnowballTarget/SnowballTarget-499976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bc0fc59d7a4e2bff036cecbbc3e61452b49bed920023cb58843a3d2ab024916
+size 271829

SnowballTarget/SnowballTarget-499976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87033b4483562aadd2c15cccf65985681dc389e51407f04e86b8f65ff2892b26
+size 2370966

SnowballTarget/SnowballTarget-500104.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8cf3d8f49f9b8fda5bde914bb99dec1f2fdbb7d59d3c7f8fd5658f57a151beb
+size 271829

SnowballTarget/SnowballTarget-500104.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b30bce1f500077ec5924bfd0e14b589df5a5beaea0ef0a6778aaccb22f5ea052
+size 2370966

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e46855ee70b06963cfa19a7705fe04fceb64ff127cfa948be3c1c57a65d1bfd
+size 2369591

SnowballTarget/events.out.tfevents.1711530714.34ee6c2b4acf.14548.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d14b89f9967d11523473210d8aba7d1c11e1d536f1dbf8c2a4fdf6cc528ddc40
+size 18270

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 1024, "buffer_size": 10240, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": true, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "curiosity": {"gamma": 0.99, "strength": 0.2, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0003, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 500000, "time_horizon": 64, "summary_freq": 50000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget3", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,92 @@
+default_settings: null
+behaviors:
+  SnowballTarget:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 1024
+      buffer_size: 10240
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      shared_critic: false
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 500000
+    network_settings:
+      normalize: true
+      hidden_units: 128
+      num_layers: 2
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+        network_settings:
+          normalize: false
+          hidden_units: 128
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+      curiosity:
+        gamma: 0.99
+        strength: 0.2
+        network_settings:
+          normalize: false
+          hidden_units: 128
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+        learning_rate: 0.0003
+        encoding_size: null
+    init_path: null
+    keep_checkpoints: 5
+    even_checkpoints: false
+    max_steps: 500000
+    time_horizon: 64
+    summary_freq: 50000
+    threaded: false
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/linux/SnowballTarget/SnowballTarget
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  timeout_wait: 60
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+  no_graphics_monitor: false
+environment_parameters: null
+checkpoint_settings:
+  run_id: SnowballTarget3
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,259 @@
+Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
+Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
+Forcing GfxDevice: Null
+GfxDevice: creating device client; threaded=0; jobified=0
+NullGfxDevice:
+    Version:  NULL 1.0 [1.0]
+    Renderer: Null Device
+    Vendor:   Unity Technologies
+ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
+ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+Forced to initialize FMOD to to the device driver's system output rate 48000, this may impact performance and/or give inconsistent experiences compared to selected sample rate 48000
+ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
+ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+FMOD initialized on nosound output
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.095 seconds
+ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Standard' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Standard' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+UnloadTime: 0.970562 ms
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+requesting resize 84 x 84
+Setting up 1 worker threads for Enlighten.
+Memory Statistics:
+[ALLOC_TEMP_TLS] TLS Allocator
+  StackAllocators : 
+    [ALLOC_TEMP_MAIN]
+      Peak usage frame count: [8.0 KB-16.0 KB]: 13412 frames, [16.0 KB-32.0 KB]: 227 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.0 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 198 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 304.0 KB
+      Peak Allocated Bytes 228.9 KB
+      Overflow Count 4
+    [ALLOC_TEMP_Background Job.Worker 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 3.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 1]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 7]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 40
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 12748 frames, [8.0 MB-16.0 MB]: 892 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 9.6 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 13640 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.8 MB
+      Peak Large allocation bytes 16.0 MB
+[ALLOC_TEMP_JOB_1_FRAME]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_2_FRAMES]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
+  Initial Block Size 2.0 MB
+  Used Block Count 2
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_ASYNC (Background)]
+  Initial Block Size 1.0 MB
+  Used Block Count 3
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_GFX] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 13104 frames, [64.0 KB-128.0 KB]: 536 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 66.4 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 13640 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 39.6 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_CACHEOBJECTS] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 13640 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 0.6 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_CACHEOBJECTS_THREAD]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 13639 frames, [2.0 MB-4.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 2.2 MB
+      Peak Large allocation bytes 0 B
+[ALLOC_TYPETREE] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 13640 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 1.0 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_TYPETREE_THREAD]
+      Peak usage frame count: [1.0 KB-2.0 KB]: 13640 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 1.7 KB
+      Peak Large allocation bytes 0 B

run_logs/timers.json

@@ -0,0 +1,410 @@
+{
+    "name": "root",
+    "gauges": {
+        "SnowballTarget.Policy.Entropy.mean": {
+            "value": 1.1493377685546875,
+            "min": 1.1493377685546875,
+            "max": 2.864180564880371,
+            "count": 10
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 57347.35546875,
+            "min": 57347.35546875,
+            "max": 144675.484375,
+            "count": 10
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 499976.0,
+            "min": 49936.0,
+            "max": 499976.0,
+            "count": 10
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 499976.0,
+            "min": 49936.0,
+            "max": 499976.0,
+            "count": 10
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 12.845760345458984,
+            "min": 0.3540566861629486,
+            "max": 12.845760345458984,
+            "count": 10
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 12884.2978515625,
+            "min": 351.2242431640625,
+            "max": 12884.2978515625,
+            "count": 10
+        },
+        "SnowballTarget.Policy.CuriosityValueEstimate.mean": {
+            "value": 0.8443097472190857,
+            "min": 0.21610280871391296,
+            "max": 1.0515366792678833,
+            "count": 10
+        },
+        "SnowballTarget.Policy.CuriosityValueEstimate.sum": {
+            "value": 846.8426513671875,
+            "min": 214.37399291992188,
+            "max": 1044.1759033203125,
+            "count": 10
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 10
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 50347.0,
+            "min": 48158.0,
+            "max": 50347.0,
+            "count": 10
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 25.893280632411066,
+            "min": 3.855371900826446,
+            "max": 25.893280632411066,
+            "count": 10
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 6551.0,
+            "min": 933.0,
+            "max": 6551.0,
+            "count": 10
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 25.893280632411066,
+            "min": 3.855371900826446,
+            "max": 25.893280632411066,
+            "count": 10
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 6551.0,
+            "min": 933.0,
+            "max": 6551.0,
+            "count": 10
+        },
+        "SnowballTarget.Policy.CuriosityReward.mean": {
+            "value": 1.624363026246723,
+            "min": 1.624363026246723,
+            "max": 2.892317029639832,
+            "count": 10
+        },
+        "SnowballTarget.Policy.CuriosityReward.sum": {
+            "value": 410.9638456404209,
+            "min": 410.9638456404209,
+            "max": 699.9407211728394,
+            "count": 10
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.022228808685273785,
+            "min": 0.0222080560298006,
+            "max": 0.026353130527180232,
+            "count": 10
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.08891523474109514,
+            "min": 0.08891523474109514,
+            "max": 0.12910080968249532,
+            "count": 10
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.13977829820166032,
+            "min": 0.07806220607211192,
+            "max": 0.19508210450410843,
+            "count": 10
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.5591131928066413,
+            "min": 0.3122488242884477,
+            "max": 0.9754105225205422,
+            "count": 10
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 1.4576495141199999e-05,
+            "min": 1.4576495141199999e-05,
+            "max": 0.0002841864052712,
+            "count": 10
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 5.8305980564799996e-05,
+            "min": 5.8305980564799996e-05,
+            "max": 0.0012797184734271998,
+            "count": 10
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.1048588,
+            "min": 0.1048588,
+            "max": 0.19472879999999998,
+            "count": 10
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.4194352,
+            "min": 0.4194352,
+            "max": 0.9265728000000001,
+            "count": 10
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 0.00025245412000000005,
+            "min": 0.00025245412000000005,
+            "max": 0.004736967120000001,
+            "count": 10
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.0010098164800000002,
+            "min": 0.0010098164800000002,
+            "max": 0.02133598272,
+            "count": 10
+        },
+        "SnowballTarget.Losses.CuriosityForwardLoss.mean": {
+            "value": 0.04066641284152865,
+            "min": 0.04066641284152865,
+            "max": 0.15649448223412038,
+            "count": 10
+        },
+        "SnowballTarget.Losses.CuriosityForwardLoss.sum": {
+            "value": 0.1626656513661146,
+            "min": 0.1626656513661146,
+            "max": 0.6259779289364815,
+            "count": 10
+        },
+        "SnowballTarget.Losses.CuriosityInverseLoss.mean": {
+            "value": 1.054714846611023,
+            "min": 1.054714846611023,
+            "max": 2.801060312986374,
+            "count": 10
+        },
+        "SnowballTarget.Losses.CuriosityInverseLoss.sum": {
+            "value": 4.218859386444092,
+            "min": 4.218859386444092,
+            "max": 12.449160003662112,
+            "count": 10
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 10
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 10
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1711530713",
+        "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget3 --no-graphics",
+        "mlagents_version": "1.1.0.dev0",
+        "mlagents_envs_version": "1.1.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.2.1+cu121",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1711531767"
+    },
+    "total": 1053.6621658160002,
+    "count": 1,
+    "self": 0.42601278500069384,
+    "children": {
+        "run_training.setup": {
+            "total": 0.06015482199973121,
+            "count": 1,
+            "self": 0.06015482199973121
+        },
+        "TrainerController.start_learning": {
+            "total": 1053.1759982089998,
+            "count": 1,
+            "self": 0.8691430139365366,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.0402573049996136,
+                    "count": 1,
+                    "self": 2.0402573049996136
+                },
+                "TrainerController.advance": {
+                    "total": 1050.1352405880639,
+                    "count": 45464,
+                    "self": 0.9238774870291309,
+                    "children": {
+                        "env_step": {
+                            "total": 752.7561935750673,
+                            "count": 45464,
+                            "self": 584.8651935689213,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 167.33226991003266,
+                                    "count": 45464,
+                                    "self": 3.134988525036988,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 164.19728138499568,
+                                            "count": 45464,
+                                            "self": 164.19728138499568
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.5587300961133224,
+                                    "count": 45464,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 1049.6666539140938,
+                                            "count": 45464,
+                                            "is_parallel": true,
+                                            "self": 537.8826951320802,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0022327749998112267,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006461329994635889,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0015866420003476378,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0015866420003476378
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.034909802000129275,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006885730003887147,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.000443045999872993,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.000443045999872993
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.03193026799999643,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.03193026799999643
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0018479149998711364,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.000360121000539948,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0014877939993311884,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0014877939993311884
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 511.78395878201354,
+                                                    "count": 45463,
+                                                    "is_parallel": true,
+                                                    "self": 25.870365160052643,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 13.876963266005987,
+                                                            "count": 45463,
+                                                            "is_parallel": true,
+                                                            "self": 13.876963266005987
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 390.81473614399374,
+                                                            "count": 45463,
+                                                            "is_parallel": true,
+                                                            "self": 390.81473614399374
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 81.22189421196117,
+                                                            "count": 45463,
+                                                            "is_parallel": true,
+                                                            "self": 14.647346818277128,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 66.57454739368404,
+                                                                    "count": 454630,
+                                                                    "is_parallel": true,
+                                                                    "self": 66.57454739368404
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 296.45516952596745,
+                            "count": 45464,
+                            "self": 1.0763309329308868,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 119.15690446203689,
+                                    "count": 45464,
+                                    "self": 119.00658910103766,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.1503153609992296,
+                                            "count": 1,
+                                            "self": 0.1503153609992296
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 176.22193413099967,
+                                    "count": 47,
+                                    "self": 146.0050128549974,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 30.216921276002267,
+                                            "count": 1410,
+                                            "self": 30.216921276002267
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 8.010001693037339e-07,
+                    "count": 1,
+                    "self": 8.010001693037339e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.13135650099957275,
+                    "count": 1,
+                    "self": 0.0007333689991355641,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.13062313200043718,
+                            "count": 1,
+                            "self": 0.13062313200043718
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,38 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 499976,
+                "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-499976.onnx",
+                "reward": 25.818181818181817,
+                "creation_time": 1711531766.5351207,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget3/SnowballTarget/SnowballTarget-499976.pt"
+                ]
+            },
+            {
+                "steps": 500104,
+                "file_path": "results/SnowballTarget3/SnowballTarget/SnowballTarget-500104.onnx",
+                "reward": 25.818181818181817,
+                "creation_time": 1711531766.6884472,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget3/SnowballTarget/SnowballTarget-500104.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 500104,
+            "file_path": "results/SnowballTarget3/SnowballTarget.onnx",
+            "reward": 25.818181818181817,
+            "creation_time": 1711531766.6884472,
+            "auxillary_file_paths": [
+                "results/SnowballTarget3/SnowballTarget/SnowballTarget-500104.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.2.1+cu121"
+    }
+}